Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3232 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.8144. Min Act: -0.1700
Data Index: 3673921 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.8144. Min Act: -0.1700
Data Index: 5842689 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.7207. Min Act: -0.1700
Data Index: 5857572 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.6582. Min Act: -0.1700
Data Index: 4023008 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.6269. Min Act: -0.1700
Data Index: 3526553 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.5957. Min Act: -0.1700
Data Index: 6078531 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.5644. Min Act: -0.1700
Data Index: 1645510 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.5332. Min Act: -0.1700
Data Index: 6447567 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.5332. Min Act: -0.1700
Data Index: 4000851 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.5332. Min Act: -0.1700
Data Index: 5095833 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.5332. Min Act: -0.1700
Data Index: 5854794 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.5332. Min Act: -0.1700
Data Index: 4533908 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4707. Min Act: -0.1700
Data Index: 634712 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.5019. Min Act: -0.1700
Data Index: 4226724 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4707. Min Act: -0.1700
Data Index: 5276208 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4707. Min Act: -0.1700
Data Index: 5935960 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4707. Min Act: -0.1700
Data Index: 2367308 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4707. Min Act: -0.1700
Data Index: 2055770 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4707. Min Act: -0.1700
Data Index: 2754716 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8144. Min Range: -4.8144
Max Act: 4.4082. Min Act: -0.1700
Data Index: 475848 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19